add tokenizer
Browse files- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.json +1 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
|
vocab.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"ج": 0, "چ": 1, "ظ": 2, "و": 3, "ئ": 4, "ض": 5, "ھ": 6, "گ": 7, "س": 8, "خ": 9, "ث": 10, "ق": 11, "ڑ": 12, "آ": 13, "ی": 14, "": 15, "ہ": 16, "ک": 17, "ڈ": 18, "م": 19, "ل": 20, "ز": 21, "ؤ": 22, "ن": 23, "د": 24, "ّ": 25, "ذ": 26, "ع": 27, "ت": 28, "پ": 29, "ف": 30, "ش": 31, "ء": 33, "ٹ": 34, "ح": 35, "ب": 36, "ا": 37, "ژ": 38, "ں": 39, "ُ": 40, "غ": 41, "ے": 42, "ر": 43, "ص": 44, "ط": 45, "|": 32, "[UNK]": 46, "[PAD]": 47}
|